NC General Statutes

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the safe read-only, idempotent, closed-world profile, and the description adds substantial context beyond them: results are derived from the section's own history note, grouped by year, deduplicated across multiple text versions, plus a first-enacted year and total amendment count. The `not_yet_in_force` entry semantics and the distinction between statutory dates and database-observed changes are exactly the kind of behavioral nuance annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the definition, then use cases, then return shape, then disambiguation against siblings. Each sentence carries distinct information — no restatement of the title or name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup with full schema coverage and an output schema, nothing needed to call it correctly is missing. The description even adds value the output schema cannot, such as the grouping, deduplication, and not_yet_in_force semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single `citation` parameter already carries examples and a description, so the schema does the heavy lifting. The description implies the citation form through its G.S. 14-33 example but adds no format or normalization guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource — when an NC statute section was enacted and each amendment date — and explicitly frames the tool around citation-level history. It is immediately distinguishable from siblings that return text (get_statute, diff_statute) rather than temporal enactment records.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives literal trigger queries ('how often has G.S. 14-33 changed', 'when was this last amended') and then names the alternatives with the condition that selects each: recent_law_changes for database-observed changes, get_statute or diff_statute for wording. Both when-to-use and when-not-to-use are covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious context beyond the annotations: counts are STATUTORY, derived from history notes rather than observations, which warns the agent about what the numbers mean. Return shape is partly described, though not full behavioral traits like pagination or how `since_year` interacts with the by-year breakdown.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded one-line summary, then usage, then an important caveat and sibling routing. Every sentence earns its place with no padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, and the description still previews the return shape. The main residual gap is the undocumented `top`/`since_year` parameters against 0% schema coverage, but overall the definition is sufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 3 parameters, so the description must compensate. It clarifies only `chapter` (omit for corpus-wide); `top` and `since_year` are left entirely to their names, with no explanation of the default count, ordering, or whether `since_year` filters all returned aggregates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific measure (legislative churn/amendment counts) on a specific resource (an NC statute chapter), and explicitly contrasts itself with amendment_history and pending_changes. An agent can distinguish it from every sibling without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete use case ('which parts of Chapter 14 keep changing'), an explicit corpus-wide mode ('Omit `chapter` for a corpus-wide view'), and names the two alternative tools with the conditions that select them (per-section vs. upcoming text).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real value beyond them by disclosing edge semantics: section-level only, with chapter-wide and 'this Article' references excluded, and clarifying OUTBOUND vs INBOUND directionality.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then usage examples, then the scope caveat and sibling pointer. Sentences are tight and each carries information, with only mild repetition between the opening line and the examples.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. The description covers purpose, usage, directionality, and inclusion/exclusion scope; the only meaningful omission is the semantics of the 'limit' parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so the description must compensate. It explains the 'direction' concept (OUTBOUND/INBOUND, default both), but the 'limit' parameter is undocumented in both the schema and the description, leaving a clear gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: which NC statutes a section cites and which cite it. It also differentiates from siblings by directing text lookups to get_statute, so an agent can route without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete example queries ('what does G.S. 14-72.1 depend on', 'what else references it') and names get_statute as the alternative for raw text. Clear context is given, though there is no explicit when-not beyond the text-lookup case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds the crucial operational caveat that observed history begins at ingest time and most sections therefore return diff: null. That failure mode and its workaround are exactly the kind of behavioral disclosure annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short blocks: what it does, how each mode is used, and what it cannot do plus the escape hatches. Every sentence earns its place and the caveats are front-loaded rather than buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return-value shape need not be described, yet the description still flags the diff: null case. Tool is read-only, no auth or rate-limit concerns to state, and the alternatives for out-of-range history are given, so an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (only citation is documented), so the description must compensate and it does: it defines the semantics of both mode values and notes that observed mode can optionally be bounded between two dates, which is the only explanation of from_date/to_date anywhere. format remains unexplained, but the two decisive parameters are covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (word-level diff) plus the exact resource (a North Carolina statute section between two versions), and immediately distinguishes its two operating modes. An agent can tell this apart from get_statute, amendment_history, and pending_changes without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes mode="pending" to the 'what will change on 1 October' question and mode="observed" to already-recorded versions, and names two alternative tools (amendment_history for earlier change dates, pending_changes for pending text) with the condition that selects each.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish the safe-read profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial behavioral context beyond them: what as_of actually resolves against, the observed-version watermark vs effective dates, how uncodified overrides are reported, and the limit that pending ratified bills appear in neither source.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Long, but front-loaded with purpose and scoping on the first line and structured into constraint-bearing paragraphs. Nearly every sentence carries a distinct, actionable warning; a small amount of repetition (as_of semantics restated) keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a citation-lookup tool with an output schema present, the description covers everything an agent needs: accepted citation spellings, section-level granularity, the Rule-as-statute special cases, and the watermark caveats. Return fields are enumerated helpfully rather than redundantly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (25%), so the description must compensate, and it does for as_of ("text observed on a past date", resolving against observed versions not effective dates) and pending ("variants enacted but not yet effective"). max_chars remains unexplained in both the description and schema, leaving one parameter undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource ("Full text of one North Carolina (NC) General Statutes section, by citation") and immediately distinguishes itself from siblings by naming amendment_history, diff_statute, recent_law_changes, and search_statutes for their respective jobs. An agent can route correctly without opening another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use ("what does G.S. 14-72.1 say"), when-to-use-alternatives ("For WHEN it changed use amendment_history; for WHAT changed use diff_statute"), and a redirect for effective-date questions ("use recent_law_changes(source=\"effective\")"). It also names exclusions (PENDING BILLS ARE NOT COVERED).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds the boundary condition that only future-dated variants count and that a diff is returned by default, which is genuinely useful behavior beyond the annotations. It does not, however, discuss result volume or how the limit/pagination interacts with the diff payload.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The scoping sentence is front-loaded, followed by a use-case, then return behavior, then the disambiguation block. Every sentence carries distinct information and the alternatives are last, which is the right ordering.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is not strictly required, yet the description helpfully summarizes what comes back. For a read-only, filtered-list tool the coverage is nearly complete; only the unexplained limit/citation parameters leave a gap, and that is scored separately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all four parameters, so the description must carry the load. It explains the default diff behavior (include_diff) and implies chapter filtering via the Chapter 14 example, but says nothing about limit, citation, or the string-vs-integer form of chapter. Two of four parameters remain undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource (NC statute text enacted but not yet effective) and distinguishes three sibling tools by name (get_statute, amendment_history, recent_law_changes). It even clarifies a subtle semantic: AMENDMENT (current text exists) vs NEW SECTION (no diff possible). An agent can route without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use ('what changes to Chapter 14 are coming') plus explicit when-not-to-use with the correct alternatives for each case ('text in force now use get_statute', 'already-enacted history use amendment_history or recent_law_changes'). Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already carry read-only/idempotent/non-destructive semantics, but the description adds genuinely non-obvious behavior: 'effective' looks forward into future effective dates, and 'observed' reflects ncleg's publishing schedule rather than the law's own timeline. That distinction is exactly the kind of caveat an agent cannot infer from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the resource and its date axes, then groups guidance by source value in short, skimmable clauses with no padding. The dense quoting style is slightly awkward but every sentence carries a distinct instruction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape is covered, and the description fully handles the semantic minefield of source selection and date pairing. It is still thin on three optional parameters (limit, chapter, include_baseline), which leaves an agent guessing when those filters are useful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 17%, so the description carries real weight here, and it does explain source semantics and the since/until pairing for a single-day query. However, limit, chapter, and include_baseline are never mentioned in either the schema or the description, so the compensation is partial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (changed NC statutes) and the axes along which they are organized (effective date, observation, session year), which is well beyond restating the name. It also names the sibling to use for a different granularity (amendment_history), letting an agent disambiguate without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly maps each source value to a question it answers ('effective' for what took effect on a day or a future quarter, 'statutory' for the legislature's history-note record, 'observed' for database-side text changes), and states 'both' returns statutory + observed. It also routes single-section lookups to amendment_history with an explicit condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only/idempotent/closed-world, and the description adds substantial non-obvious behavior: match_mode semantics with all four values explained, automatic court-shorthand expansion reported as expanded_query, terms_matched ranking order, nearest-number suggestions for bare citations, and the interpretive rule that a low top rank means no on-point statute. This is exactly the extra context the annotation bar invites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Long but front-loaded: purpose, routing rule, and return-shape caveat come first, then query syntax and match_mode details. Every sentence carries operational information (expansion, ranking, suggestions), though the match_mode enumeration and ranking explanation could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be enumerated, yet the description still clarifies the shape that matters (ranked fragments with highlights, not full text) and the fields an agent must react to (match_mode, expanded_query, suggestions). For a 4-param search tool this leaves no material gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25%, so the description must carry the load, and it does for the dominant parameter: query syntax (quoted phrases, -exclusions, `or`), shorthand expansion and how the query is interpreted. However, limit, chapter and include_repealed are never addressed; 'the law in force today' only implicitly signals include_repealed=false, and chapter scoping is unmentioned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search North Carolina (NC) statutes') plus scope ('by topic, keyword or phrase') and instantly separates itself from get_statute by citation-vs-subject framing. An agent can distinguish it from every sibling without reading schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use ('when you know the SUBJECT but not the citation') with concrete example queries, and an explicit when-not with the named alternative ('If you already have a citation, use get_statute instead'). It also tells the agent what to do next after a hit (pick one, call get_statute).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.